Colin Schmidt
0a6c05a5d8
connect top level interrupts to coreplex
2016-08-18 15:52:44 -07:00
Howard Mao
91a97d6773
add some more comments to describe the new device system
2016-08-18 15:06:55 -07:00
Howard Mao
1b6fa70b5c
Add test for external TL clients (bus mastering)
2016-08-18 14:26:03 -07:00
Howard Mao
18982d7351
add default addrMapEntry definition which throws exception
2016-08-18 12:29:41 -07:00
Howard Mao
f7c42499bb
allow ExtraDevices to have client ports as well as MMIO ports
2016-08-18 12:18:14 -07:00
Howard Mao
d771f37e7e
rename BusPorts to ExternalClients
2016-08-18 10:54:24 -07:00
Howard Mao
10190197c3
allow coreplex to take in more than 1 bus port
2016-08-18 10:35:25 -07:00
David Biancolin
de316643d1
Merge pull request #205 from ucb-bar/configurable_memsize
...
make memsize configurable
2016-08-17 18:33:56 -07:00
David Biancolin
29600f64ec
make memsize configurable
2016-08-17 16:31:34 -07:00
Andrew Waterman
5164f947c0
Validate mstatus.mpp/dcsr.prv values on MRET/DRET
...
The registers can still hold invalid values, but an attempt to switch
to the mode stored therein will instead go to an implemented mode.
2016-08-17 15:39:34 -07:00
Howard Mao
35fbbfc70d
put test harness on the heap in emulator
2016-08-16 14:50:40 -07:00
Andrew Waterman
ed827678ac
Write test harness in Chisel
...
This is an unavoidably invasive commit, because it affects the unit tests
(which formerly exited using stop()), the test harness Verilog generator
(since it is no longer necessary), and the DRAM model (since it is no
longer connected). However, this should substantially reduce the effort
of building test harnesses in the future, since manual or semi-automatic
Verilog writing should no longer be necessary. Furthermore, there is now
very little duplication of effort between the Verilator and VCS test
harnesses.
This commit removes support for DRAMsim, which is a bit of an unfortunate
consequence. The main blocker is the lack of Verilog parameterization for
BlackBox. It would be straightforward to revive DRAMsim once support for
that feature is added to Chisel and FIRRTL. But that might not even be
necessary, as we move towards synthesizable DRAM models and FAME-1
transformations.
2016-08-15 23:27:27 -07:00
Andrew Waterman
2d1d7266f5
Fix RV64 badaddr value on instruction faults with large addresses
...
We were relying on ALU passthrough for this, but failed to override the
ALU dw argument, so bits above 31 could be discarded.
2016-08-15 23:09:09 -07:00
Howard Mao
38e0967816
strip DMA and RoCC CSRs out of rocket and uncore ( #201 )
2016-08-15 23:08:55 -07:00
Howard Mao
47a0c880a4
make sure TLId set in Periphery
2016-08-15 13:58:23 -07:00
Howard Mao
e939af88aa
explicitly set TLId for bus TL ports
2016-08-15 12:46:29 -07:00
Howard Mao
2c39f039b5
make external address map order overrideable
2016-08-15 11:40:28 -07:00
Howard Mao
fb476d193c
refactor main App for better code re-use
2016-08-11 16:15:23 -07:00
Howard Mao
a756856d84
make sure coreplex sources included in make dependencies
2016-08-11 14:27:03 -07:00
Howard Mao
e0ae039235
fix config string generation for extra devices
2016-08-11 10:44:32 -07:00
Howard Mao
647dbefd9b
split coreplex off into separate package
2016-08-10 18:04:22 -07:00
Howard Mao
163cba6a85
make sure all regressions actually run
2016-08-10 14:52:06 -07:00
Howard Mao
4bfa7ceb6a
unit tests in Coreplex instead of Tile
2016-08-10 11:26:14 -07:00
Howard Mao
571d579b86
get unit tests working again
2016-08-10 11:23:07 -07:00
Howard Mao
0ee1ce4366
separate Coreplex and TopLevel parameter traits
2016-08-10 09:49:56 -07:00
Howard Mao
f95d319162
don't use secondary external address map; collapse submap instead
2016-08-09 22:29:38 -07:00
Howard Mao
2645f74af2
clean up addrmap flatten function
2016-08-09 22:14:32 -07:00
Howard Mao
33f13d5c49
don't repeat external addr map base
2016-08-09 21:20:54 -07:00
Howard Mao
3ea2f4a6c4
refactor top-level into coreplex and platform
2016-08-09 18:26:52 -07:00
Howard Mao
993da60f2c
relax address map alignment requirement
2016-08-09 18:25:32 -07:00
Howard Mao
33d5905c50
don't synthesize vsim verilog in Travis
2016-08-09 18:24:59 -07:00
Howard Mao
405294167f
fix TL -> Nasti converter w id
2016-08-09 18:24:23 -07:00
Andrew Waterman
2906c75167
Remove fsim, as it is the same as vsim, modulo CONFIG
2016-08-09 15:42:22 -07:00
Andrew Waterman
1b8f919db2
Remove unused CoreName parameter
2016-08-09 15:24:59 -07:00
Andrew Waterman
458520c8f6
Use a generic UInt for TileLink op sizes, rather than MT_xx enum
2016-08-09 15:24:51 -07:00
Andrew Waterman
a857b08c59
[rocket] compute D$ tag bits based upon # of arbiter ports
2016-08-09 14:40:48 -07:00
Howard Mao
2a5aeeae24
add sbt pack plugin ( #197 )
2016-08-08 19:31:03 -07:00
Howard Mao
dd1fed41b6
generate BootROM contents from assembly code
2016-08-05 16:39:21 -07:00
Palmer Dabbelt
dab96096b4
Add firrtl build dependencies
...
Without this when I update firrtl the new version doesn't get built, so
my build is constantly failing.
2016-08-05 14:45:00 -07:00
Howard Mao
9fa5b228b2
allow extra devices and top-level ports to be added without changing RocketChip.scala
2016-08-04 14:06:14 -07:00
Howard Mao
9c4e57aea5
example Rocc accelerator fixes
2016-08-04 11:17:13 -07:00
Howard Mao
410e3e5366
make sure TraceGen gets correct addresses
2016-08-04 11:08:25 -07:00
Howard Mao
0a85e92652
Allow additional internal MMIO devices to be created without changing BaseConfig
2016-08-04 11:04:52 -07:00
Andrew Waterman
cc0f8962fb
[rocket] take physical memory attribute check off critical path
...
Cache the attributes in the TLB instead.
2016-08-02 17:21:03 -07:00
Andrew Waterman
76f33d88a6
[rocket] Respect physical memory protection during page table walks
2016-08-02 17:20:49 -07:00
Andrew Waterman
5d4f6383f2
[rocket] Automatically kill D$ access on address exceptions
...
Doing this internally to the cache eliminates a long control path
from the cache to the core and back to the cache.
2016-08-02 17:20:49 -07:00
Andrew Waterman
b54db0ba23
[rocket] don't update BTB on not-taken branches
...
Only update the BHT; don't set the target prediction to pc+4.
2016-08-02 17:20:49 -07:00
Andrew Waterman
64bde1060c
[rocket] remove unused code in ibuf
2016-08-02 15:26:09 -07:00
Andrew Waterman
2ce702dc0a
[rocket] fix PTW critical path
...
Pipeline the killing of a D$ request following a PTW cache hit.
2016-08-02 15:19:48 -07:00
Andrew Waterman
7e9d139e49
[rocket] remove rocket-specific require() from HasCoreParameters
2016-08-02 15:19:48 -07:00